@inproceedings{miyazaki-etal-2021-fundamental,
title = "Fundamental Exploration of Evaluation Metrics for Persona Characteristics of Text Utterances",
author = "Miyazaki, Chiaki and
Kanno, Saya and
Yoda, Makoto and
Ono, Junya and
Wakaki, Hiromi",
editor = "Li, Haizhou and
Levow, Gina-Anne and
Yu, Zhou and
Gupta, Chitralekha and
Sisman, Berrak and
Cai, Siqi and
Vandyke, David and
Dethlefs, Nina and
Wu, Yan and
Li, Junyi Jessy",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.19",
doi = "10.18653/v1/2021.sigdial-1.19",
pages = "178--189",
abstract = "To maintain utterance quality of a persona-aware dialog system, inappropriate utterances for the persona should be thoroughly filtered. When evaluating the appropriateness of a large number of arbitrary utterances to be registered in the utterance database of a retrieval-based dialog system, evaluation metrics that require a reference (or a {``}correct{''} utterance) for each evaluation target cannot be used. In addition, practical utterance filtering requires the ability to select utterances based on the intensity of persona characteristics. Therefore, we are developing metrics that can be used to capture the intensity of persona characteristics and can be computed without references tailored to the evaluation targets. To this end, we explore existing metrics and propose two new metrics: persona speaker probability and persona term salience. Experimental results show that our proposed metrics show weak to moderate correlations between scores of persona characteristics based on human judgments and outperform other metrics overall in filtering inappropriate utterances for particular personas.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miyazaki-etal-2021-fundamental">
<titleInfo>
<title>Fundamental Exploration of Evaluation Metrics for Persona Characteristics of Text Utterances</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chiaki</namePart>
<namePart type="family">Miyazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saya</namePart>
<namePart type="family">Kanno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Yoda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junya</namePart>
<namePart type="family">Ono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiromi</namePart>
<namePart type="family">Wakaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitralekha</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To maintain utterance quality of a persona-aware dialog system, inappropriate utterances for the persona should be thoroughly filtered. When evaluating the appropriateness of a large number of arbitrary utterances to be registered in the utterance database of a retrieval-based dialog system, evaluation metrics that require a reference (or a “correct” utterance) for each evaluation target cannot be used. In addition, practical utterance filtering requires the ability to select utterances based on the intensity of persona characteristics. Therefore, we are developing metrics that can be used to capture the intensity of persona characteristics and can be computed without references tailored to the evaluation targets. To this end, we explore existing metrics and propose two new metrics: persona speaker probability and persona term salience. Experimental results show that our proposed metrics show weak to moderate correlations between scores of persona characteristics based on human judgments and outperform other metrics overall in filtering inappropriate utterances for particular personas.</abstract>
<identifier type="citekey">miyazaki-etal-2021-fundamental</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.19</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.19</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>178</start>
<end>189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fundamental Exploration of Evaluation Metrics for Persona Characteristics of Text Utterances
%A Miyazaki, Chiaki
%A Kanno, Saya
%A Yoda, Makoto
%A Ono, Junya
%A Wakaki, Hiromi
%Y Li, Haizhou
%Y Levow, Gina-Anne
%Y Yu, Zhou
%Y Gupta, Chitralekha
%Y Sisman, Berrak
%Y Cai, Siqi
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Wu, Yan
%Y Li, Junyi Jessy
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 July
%I Association for Computational Linguistics
%C Singapore and Online
%F miyazaki-etal-2021-fundamental
%X To maintain utterance quality of a persona-aware dialog system, inappropriate utterances for the persona should be thoroughly filtered. When evaluating the appropriateness of a large number of arbitrary utterances to be registered in the utterance database of a retrieval-based dialog system, evaluation metrics that require a reference (or a “correct” utterance) for each evaluation target cannot be used. In addition, practical utterance filtering requires the ability to select utterances based on the intensity of persona characteristics. Therefore, we are developing metrics that can be used to capture the intensity of persona characteristics and can be computed without references tailored to the evaluation targets. To this end, we explore existing metrics and propose two new metrics: persona speaker probability and persona term salience. Experimental results show that our proposed metrics show weak to moderate correlations between scores of persona characteristics based on human judgments and outperform other metrics overall in filtering inappropriate utterances for particular personas.
%R 10.18653/v1/2021.sigdial-1.19
%U https://aclanthology.org/2021.sigdial-1.19
%U https://doi.org/10.18653/v1/2021.sigdial-1.19
%P 178-189
Markdown (Informal)
[Fundamental Exploration of Evaluation Metrics for Persona Characteristics of Text Utterances](https://aclanthology.org/2021.sigdial-1.19) (Miyazaki et al., SIGDIAL 2021)
ACL